Matches in SemOpenAlex for { <https://semopenalex.org/work/W2913608349> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2913608349 endingPage "3015" @default.
- W2913608349 startingPage "3003" @default.
- W2913608349 abstract "This paper considers the scenario that multiple data owners wish to apply a machine learning method over the combined dataset of all owners to obtain the best possible learning output but do not want to share the local datasets owing to privacy concerns. We design systems for the scenario that the stochastic gradient descent (SGD) algorithm is used as the machine learning method because SGD (or its variants) is at the heart of recent deep learning techniques over neural networks. Our systems differ from existing systems in the following features: {bf (1)} any activation function can be used, meaning that no privacy-preserving-friendly approximation is required; {bf (2)} gradients computed by SGD are not shared but the weight parameters are shared instead; and {bf (3)} robustness against colluding parties even in the extreme case that only one honest party exists. We prove that our systems, while privacy-preserving, achieve the same learning accuracy as SGD and hence retain the merit of deep learning with respect to accuracy. Finally, we conduct several experiments using benchmark datasets, and show that our systems outperform previous system in terms of learning accuracies." @default.
- W2913608349 created "2019-02-21" @default.
- W2913608349 creator A5068171354 @default.
- W2913608349 creator A5077849046 @default.
- W2913608349 date "2019-11-01" @default.
- W2913608349 modified "2023-10-12" @default.
- W2913608349 title "Privacy-Preserving Deep Learning via Weight Transmission" @default.
- W2913608349 cites W1515782956 @default.
- W2913608349 cites W1985511977 @default.
- W2913608349 cites W1992926795 @default.
- W2913608349 cites W2053637704 @default.
- W2913608349 cites W2106313770 @default.
- W2913608349 cites W2112796928 @default.
- W2913608349 cites W2167372639 @default.
- W2913608349 cites W2194775991 @default.
- W2913608349 cites W2233233025 @default.
- W2913608349 cites W2295292576 @default.
- W2913608349 cites W2473418344 @default.
- W2913608349 cites W2481704219 @default.
- W2913608349 cites W2535690855 @default.
- W2913608349 cites W2591882872 @default.
- W2913608349 cites W2620512600 @default.
- W2913608349 cites W2701059868 @default.
- W2913608349 cites W2738182386 @default.
- W2913608349 cites W2765200655 @default.
- W2913608349 cites W2767079719 @default.
- W2913608349 cites W2781091734 @default.
- W2913608349 cites W2795354529 @default.
- W2913608349 cites W2801491268 @default.
- W2913608349 cites W2884943453 @default.
- W2913608349 cites W2895865029 @default.
- W2913608349 cites W2963106566 @default.
- W2913608349 cites W2963999993 @default.
- W2913608349 doi "https://doi.org/10.1109/tifs.2019.2911169" @default.
- W2913608349 hasPublicationYear "2019" @default.
- W2913608349 type Work @default.
- W2913608349 sameAs 2913608349 @default.
- W2913608349 citedByCount "61" @default.
- W2913608349 countsByYear W29136083492019 @default.
- W2913608349 countsByYear W29136083492020 @default.
- W2913608349 countsByYear W29136083492021 @default.
- W2913608349 countsByYear W29136083492022 @default.
- W2913608349 countsByYear W29136083492023 @default.
- W2913608349 crossrefType "journal-article" @default.
- W2913608349 hasAuthorship W2913608349A5068171354 @default.
- W2913608349 hasAuthorship W2913608349A5077849046 @default.
- W2913608349 hasBestOaLocation W29136083492 @default.
- W2913608349 hasConcept C104317684 @default.
- W2913608349 hasConcept C108583219 @default.
- W2913608349 hasConcept C119857082 @default.
- W2913608349 hasConcept C13280743 @default.
- W2913608349 hasConcept C154945302 @default.
- W2913608349 hasConcept C185592680 @default.
- W2913608349 hasConcept C185798385 @default.
- W2913608349 hasConcept C205649164 @default.
- W2913608349 hasConcept C206688291 @default.
- W2913608349 hasConcept C2984842247 @default.
- W2913608349 hasConcept C41008148 @default.
- W2913608349 hasConcept C50644808 @default.
- W2913608349 hasConcept C55493867 @default.
- W2913608349 hasConcept C63479239 @default.
- W2913608349 hasConceptScore W2913608349C104317684 @default.
- W2913608349 hasConceptScore W2913608349C108583219 @default.
- W2913608349 hasConceptScore W2913608349C119857082 @default.
- W2913608349 hasConceptScore W2913608349C13280743 @default.
- W2913608349 hasConceptScore W2913608349C154945302 @default.
- W2913608349 hasConceptScore W2913608349C185592680 @default.
- W2913608349 hasConceptScore W2913608349C185798385 @default.
- W2913608349 hasConceptScore W2913608349C205649164 @default.
- W2913608349 hasConceptScore W2913608349C206688291 @default.
- W2913608349 hasConceptScore W2913608349C2984842247 @default.
- W2913608349 hasConceptScore W2913608349C41008148 @default.
- W2913608349 hasConceptScore W2913608349C50644808 @default.
- W2913608349 hasConceptScore W2913608349C55493867 @default.
- W2913608349 hasConceptScore W2913608349C63479239 @default.
- W2913608349 hasFunder F4320334789 @default.
- W2913608349 hasIssue "11" @default.
- W2913608349 hasLocation W29136083491 @default.
- W2913608349 hasLocation W29136083492 @default.
- W2913608349 hasOpenAccess W2913608349 @default.
- W2913608349 hasPrimaryLocation W29136083491 @default.
- W2913608349 hasRelatedWork W2610321374 @default.
- W2913608349 hasRelatedWork W2790244305 @default.
- W2913608349 hasRelatedWork W2792987183 @default.
- W2913608349 hasRelatedWork W2950066684 @default.
- W2913608349 hasRelatedWork W2952919291 @default.
- W2913608349 hasRelatedWork W3082895349 @default.
- W2913608349 hasRelatedWork W3193857078 @default.
- W2913608349 hasRelatedWork W4288853838 @default.
- W2913608349 hasRelatedWork W4298388782 @default.
- W2913608349 hasRelatedWork W4308112567 @default.
- W2913608349 hasVolume "14" @default.
- W2913608349 isParatext "false" @default.
- W2913608349 isRetracted "false" @default.
- W2913608349 magId "2913608349" @default.
- W2913608349 workType "article" @default.